Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4959 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.9820. Min Act: -0.0000

Data Index: 345369 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.8989. Min Act: -0.0000

Data Index: 355107 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.8886. Min Act: -0.0000

Data Index: 1072214 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.8428. Min Act: -0.0000

Data Index: 26687 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.8549. Min Act: -0.0000

Data Index: 668067 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.8569. Min Act: -0.0001

Data Index: 813096 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.8790. Min Act: -0.0000

Data Index: 497354 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.8126. Min Act: -0.0000

Data Index: 140157 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.7774. Min Act: -0.0000

Data Index: 660936 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.7613. Min Act: -0.0000

Data Index: 225438 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.7848. Min Act: -0.0000

Data Index: 1167543 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.7270. Min Act: -0.0000

Data Index: 127234 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.7232. Min Act: -0.0001

Data Index: 1231572 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.6902. Min Act: -0.0000

Data Index: 847986 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.7297. Min Act: -0.0000

Data Index: 425901 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.7321. Min Act: -0.0000

Data Index: 348717 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.7067. Min Act: -0.0000

Data Index: 1090104 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.7043. Min Act: -0.0000

Data Index: 284699 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.7141. Min Act: -0.0000

Data Index: 512532 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.7077. Min Act: -0.0000

Data Index: 534658 (C4 (Web Text))

Max Activating Token Index: 607